skills/saadshahd/moo.md/consult/Gen Agent Trust Hub

consult

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a persona-based consulting framework by leveraging a collection of 93 markdown files representing expert profiles. These profiles contain biographical and philosophical data for high-level technical consultation.
  • [SAFE]: No executable scripts, shell commands, or network operations were found within the skill's instructions or its supporting files.
  • [SAFE]: The SKILL.md instructions define a rigid output format that restricts the agent to carrying only specific 'chosen changes' into the work, minimizing the risk of prompt leakage or unintended behavior.
  • [SAFE]: Expert profiles include discussions on security concepts (e.g., prompt injection, the 'lethal trifecta' of data exfiltration) purely as educational context for the agent's persona-based reasoning, not as instructions for malicious action.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 12:44 AM